Conventional Change Detection Methods Research Articles

Deep learning for change detection in remote sensing: a review

ABSTRACT A large number of publications have incorporated deep learning in the process of remote sensing change detection. In these Deep Learning Change Detection (DLCD) publications, deep learning methods have demonstrated their superiority over conventional change detection methods. However, the theoretical underpinnings of why deep learning improves the performance of change detection remain unresolved. As of today, few in-depth reviews have investigated the mechanisms of DLCD. Without such a review, five critical questions remain unclear. Does DLCD provide improved information representation for change detection? If so, how? How to select an appropriate DLCD method and why? How much does each type of change benefits from DLCD in terms of its performance? What are the major limitations of existing DLCD methods and what are the prospects for DLCD? To address these five questions, we reviewed according to the following strategies. We grouped the DLCD information assemblages into the four unique dimensions of remote sensing: spectral, spatial, temporal, and multi-sensor. For the extraction of information in each dimension, the difference between DLCD and conventional change detection methods was compared. We proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools: separate and coupled models. Their advantages, limitations, applicability, and performance were thoroughly investigated and explicitly presented. We examined the variations in performance between DLCD and conventional change detection. We depicted two limitations of DLCD, i.e. training sample and hardware and software dilemmas. Based on these analyses, we identified directions for future developments. As a result of our review, we found that DLCD’s advantages over conventional change detection can be attributed to three factors: improved information representation; improved change detection methods; and performance enhancements. DLCD has to surpass the limitations with regard to training samples and computing infrastructure. We envision this review can boost developments of deep learning in change detection applications.

Robust fusion algorithms for unsupervised change detection between multi-band optical images — A comprehensive case study

Unsupervised change detection techniques are generally constrained to two multi-band optical images acquired at different times through sensors sharing the same spatial and spectral resolution. In the case of the optical modality, largely studied in the remote sensing community, a straight comparison of homologous pixels such as pixel-wise differencing is suitable. However, in some specific cases such as emergency situations, punctual missions, defense and security, the only available images may be those acquired through different kinds of sensors with different resolutions. Recently some change detection techniques, dealing with images with different spatial and spectral resolutions, have been proposed. Nevertheless, they are focused on a specific scenario where one image has a high spatial and low spectral resolution while the other has a low spatial and high spectral resolution. This paper addresses the problem of detecting changes between any two multi-band optical images disregarding their spatial and spectral resolution disparities. To overcome resolution disparity, state-of-the art methods apply conventional change detection methods after preprocessing steps applied independently on the two images, e.g. resampling operations intended to reach the same spatial and spectral resolutions. Nevertheless, these preprocessing steps may waste relevant information since they do not take into account the strong interplay existing between the two images. Conversely, in this paper, we propose a method that more effectively uses the available information by modeling the two observed images as spatially and spectrally degraded versions of two (unobserved) latent images characterized by the same high spatial and high spectral resolutions. Covering the same scene, the latent images are expected to be globally similar except for possible changes in spatially sparse locations. Thus, the change detection task is envisioned through a robust fusion task which enforces the differences between the estimated latent images to be spatially sparse. We show that this robust fusion can be formulated as an inverse problem which is iteratively solved using an alternating minimization strategy. The proposed framework is implemented for an exhaustive list of applicative scenarios and applied to real multi-band optical images. A comparison with state-of-the-art change detection methods evidences the accuracy and the versatility of the proposed robust fusion-based strategy.

Change Detection in Aerial Images Using Three-Dimensional Feature Maps

Interest in aerial image analysis has increased owing to recent developments in and availability of aerial imaging technologies, like unmanned aerial vehicles (UAVs), as well as a growing need for autonomous surveillance systems. Variant illumination, intensity noise, and different viewpoints are among the main challenges to overcome in order to determine changes in aerial images. In this paper, we present a robust method for change detection in aerial images. To accomplish this, the method extracts three-dimensional (3D) features for segmentation of objects above a defined reference surface at each instant. The acquired 3D feature maps, with two measurements, are then used to determine changes in a scene over time. In addition, the important parameters that affect measurement, such as the camera’s sampling rate, image resolution, the height of the drone, and the pixel’s height information, are investigated through a mathematical model. To exhibit its applicability, the proposed method has been evaluated on aerial images of various real-world locations and the results are promising. The performance indicates the robustness of the method in addressing the problems of conventional change detection methods, such as intensity differences and shadows.

Detecting Metachanges in Data Streams from the Viewpoint of the MDL Principle

This paper addresses the issue of how we can detect changes of changes, which we call metachanges, in data streams. A metachange refers to a change in patterns of when and how changes occur, referred to as “metachanges along time” and “metachanges along state”, respectively. Metachanges along time mean that the intervals between change points significantly vary, whereas metachanges along state mean that the magnitude of changes varies. It is practically important to detect metachanges because they may be early warning signals of important events. This paper introduces a novel notion of metachange statistics as a measure of the degree of a metachange. The key idea is to integrate metachanges along both time and state in terms of “code length” according to the minimum description length (MDL) principle. We develop an online metachange detection algorithm (MCD) based on the statistics to apply it to a data stream. With synthetic datasets, we demonstrated that MCD detects metachanges earlier and more accurately than existing methods. With real datasets, we demonstrated that MCD can lead to the discovery of important events that might be overlooked by conventional change detection methods.

Change Detection Based on Deep Siamese Convolutional Network for Optical Aerial Images

In this letter, we propose a novel supervised change detection method based on a deep siamese convolutional network for optical aerial images. We train a siamese convolutional network using the weighted contrastive loss. The novelty of the method is that the siamese network is learned to extract features directly from the image pairs. Compared with hand-crafted features used by the conventional change detection method, the extracted features are more abstract and robust. Furthermore, because of the advantage of the weighted contrastive loss function, the features have a unique property: the feature vectors of the changed pixel pair are far away from each other, while the ones of the unchanged pixel pair are close. Therefore, we use the distance of the feature vectors to detect changes between the image pair. Simple threshold segmentation on the distance map can even obtain good performance. For improvement, we use a $k$ -nearest neighbor approach to update the initial result. Experimental results show that the proposed method produces results comparable, even better, with the two state-of-the-art methods in terms of F-measure.

Environmental monitoring and assessment of landscape dynamics in southern coast of the Caspian Sea through intensity analysis and imprecise land-use data.

A hierarchical intensity analysis of land-use change is applied to evaluate the dynamics of a coupled urban coastal system in Rasht County, Iran. Temporal land-use layers of 1987, 1999, and 2011 are employed, while spatial accuracy metrics are only available for 2011 data (overall accuracy of 94%). The errors in 1987 and 1999 layers are unknown, which can influence the accuracy of temporal change information. Such data were employed to examine the size and the type of errors that could justify deviations from uniform change intensities. Accordingly, errors comprising 3.31 and 7.47% of 1999 and 2011 maps, respectively, could explain all differences from uniform gains and errors including 5.21 and 1.81% of 1987 and 1999 maps, respectively, could explain all deviations from uniform losses. Additional historical information is also applied for uncertainty assessment and to separate probable map errors from actual land-use changes. In this regard, historical processes in Rasht County can explain different types of transition that are either consistent or inconsistent to known processes. The intensity analysis assisted in identification of systematic transitions and detection of competitive categories, which cannot be investigated through conventional change detection methods. Based on results, built-up area is the most active gaining category in the area and wetland category with less areal extent is more sensitive to intense land-use change processes. Uncertainty assessment results also indicated that there are no considerable classification errors in temporal land-use data and these imprecise layers can reliably provide implications for informed decision making.

Building change detection using multi-sensor and multi-view- angle imagery

Change detection of buildings in urban areas is very challenging due to geometric distortions in very high resolution (VHR). These distortions create problems in the co-registration of different images. Thus, it is very problematic to exploit images acquired by different sensors and different view angles using conventional change detection methods. Therefore, the majority of studies in this field avoid using multi-sensor and multi-view angle images. In this study, a novel co-registration method, called Patch-Wise Co-Registration (PWCR), is used to contribute to a solution of the problem. This method integrates the sensor model parameters into the co-registration process to relate corresponding pixels. From the corresponding pixels, corresponding segments (patches) are generated. Later on, the brightness values of the matching pixels/segments are compared in order to detect changes. Here, a Multivariate Alteration Detection (MAD) transform is used for identifying the changed segments. The proposed method provides the opportunity to utilize various images as bitemporal sets for change detection.

A Spatial‐Context‐Based Approach for Automated Spatial Change Analysis of Piece‐Wise Linear Building Elements

AbstractChanges of designs and construction plans often cause propagative design modifications, tedious construction coordination, cascading effects of errors, reworks, and delays in project management. Among various building elements, those having piece‐wise linear geometries (i.e., connected straight line segments), such as connected straight sections of ducts in mechanical, electrical, and plumbing systems, frequently undergo spatial changes in response to the changes of their surroundings. On the other hand, the piece‐wise linear geometries pose challenges to analyzing and controlling changes in construction and facility management. State‐of‐the‐art 3D change detection algorithms often face ambiguities about which points belong to which objects when piece‐wise linear object are spacked in small spaces. This article examines a spatial‐context‐based framework that uses spatial relationships between piece‐wise linear building elements (ducts in this article) to enable fast and reliable association of 3D data with ducts in as‐designed models for supporting reliable change analysis. Three case studies showed that this framework outperformed a conventional change detection method, and could handle large dislocations of piece‐wise linear elements and occlusions.

Cyclone damage detection on building structures from pre- and post-satellite images using wavelet based pattern recognition

The majority of building structural losses during the past few decades has been due to wind induced damage, especially tropical cyclone damages. Rapid identification of damage locations as well as damaged buildings, and appropriate maintenance, can diminish the impact of such natural disasters. This paper describes detection of damage to cyclone-prone building roof structures from pre- and post-storm satellite images of the shores of Punta Gorda before and after the Hurricane ‘Charley’ 2004 disaster using a wavelet-based change detection method. Damaged buildings are automatically identified using wavelet-extracted statistical features and by edge detection, and classification using Artificial Neural Network (ANN) and Support Vector Machine (SVM). A comparison analysis is then carried out by comparing these results with results obtained using conventional change detection methods. It is observed that the wavelet-based change detection method yields identification information of damaged buildings superior to that obtained using conventional methods. In this work, the percentage of the damaged area of each damaged building is also calculated by a newly introduced texture-wavelet analysis on roof-tops, and the results are validated by counting the damage pixels manually. A positive increase in the extracted statistical features is observed as the percentage area of damage increases, which adds to the accuracy of the identification method.

Detecting Changes in Retinal Function: Analysis with Non-Stationary Weibull Error Regression and Spatial Enhancement (ANSWERS)

Visual fields measured with standard automated perimetry are a benchmark test for determining retinal function in ocular pathologies such as glaucoma. Their monitoring over time is crucial in detecting change in disease course and, therefore, in prompting clinical intervention and defining endpoints in clinical trials of new therapies. However, conventional change detection methods do not take into account non-stationary measurement variability or spatial correlation present in these measures. An inferential statistical model, denoted ‘Analysis with Non-Stationary Weibull Error Regression and Spatial enhancement’ (ANSWERS), was proposed. In contrast to commonly used ordinary linear regression models, which assume normally distributed errors, ANSWERS incorporates non-stationary variability modelled as a mixture of Weibull distributions. Spatial correlation of measurements was also included into the model using a Bayesian framework. It was evaluated using a large dataset of visual field measurements acquired from electronic health records, and was compared with other widely used methods for detecting deterioration in retinal function. ANSWERS was able to detect deterioration significantly earlier than conventional methods, at matched false positive rates. Statistical sensitivity in detecting deterioration was also significantly better, especially in short time series. Furthermore, the spatial correlation utilised in ANSWERS was shown to improve the ability to detect deterioration, compared to equivalent models without spatial correlation, especially in short follow-up series. ANSWERS is a new efficient method for detecting changes in retinal function. It allows for better detection of change, more efficient endpoints and can potentially shorten the time in clinical trials for new therapies.

Urban building damage detection from very high resolution imagery using OCSVM and spatial features

The availability of commercial very high resolution (VHR) satellite imagery makes it possible to detect and assess building damage in the aftermath of earthquake disasters using these data. Although conventional change detection methods may be used to assess the building damage, the analysis is directed to all classes, both damaged and undamaged, but is not focused on the class of interest. In this paper, we proposed to detect the building damage in urban environments from multitemporal VHR image data using the One-Class Support Vector Machine (OCSVM), a recently developed one-class classifier, which requires training samples from the building damage only. This was illustrated with building damage detection in an urban environment from multitemporal Quickbird images. The detection was conducted at pixel level and object level. Different input vectors for the OCSVM classifier were tested in order to assess the discrimination power of spectral and spatial features: pixel level spectral features and texture features, as well as object‐based features. The results showed that the OCSVM performed better on the object level, with an overall accuracy of 82.33% and a kappa coefficient of 60.09%. The results also showed that the OCSVM provides a useful framework that can combine different features and focus on the building damage class of interest. More spatial features are needed to be exploited to obtain more accurate detection results in future studies.